** Position: **PhD Candidate

** Current Institution:** UC Berkeley

** Abstract:** Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism

Offline (or batch) reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offline dataset two main categories of methods are used: imitation learning which is suitable for expert datasets and vanilla offline RL which often requires uniform coverage datasets. From a practical standpoint datasets often deviate from these two extremes and the exact data composition is usually unknown a priori. To bridge this gap we present a new offline RL framework that smoothly interpolates between the two extremes of data composition hence unifying imitation learning and vanilla offline RL. The new framework is centered around a weak version of the concentrability coefficient that measures the deviation from the behavior policy to the expert policy alone. Under this new framework we further investigate the question on algorithm design: can one develop an algorithm that achieves a minimax optimal rate and also adapts to unknown data composition? To address this question we consider a lower confidence bound (LCB) algorithm developed based on pessimism in the face of uncertainty in offline RL. We study finite-sample properties of LCB as well as information-theoretic limits in three settings: multi-armed bandits contextual bandits and Markov decision processes (MDPs). Our analysis reveals surprising facts about optimality rates. In particular in all three settings LCB achieves a faster rate of 1/N for nearly-expert datasets compared to the usual rate of 1/sqrt{N} in offline RL where N is the number of samples in the batch dataset. In the case of contextual bandits with at least two contexts we prove that LCB is adaptively optimal for the entire data composition range achieving a smooth transition from imitation learning to offline RL. We further show that LCB is almost adaptively optimal in MDPs.

**Bio:**

Paria Rashidinejad is a Ph.D. candidate in Electrical Engineering and Computer Sciences at University of California Berkeley advised by Prof. Stuart Russell. She received her bachelor’s degree in Electrical Engineering from Sharif University of Technology. Paria is a member of the Berkeley AI Research (BAIR) Lab and the Center for Human-Compatible AI (CHAI). Her research interests lie in the areas of machine learning statistics and optimization. She is currently focused on the theory and application of reinforcement learning and developing efficient algorithms for inference and prediction in dynamical systems. She is also interested in the application of these algorithms to the real-world problems that arise in robotics finance and healthcare.